AI & Data
A RAG engine, document assistants, AI agents and chatbots that answer with links to sources. From prototype to production — on our own technology.
What we do
RAG engine
Hybrid search: vectors and word-form-aware BM25 in one SQLite, catalog field filters, answers with links to the exact document sections.
AI assistants
Assistants over the corporate base: document → precise answer with a source, not “just a chatbot”.
Agents with actions
Tool-use agents that not only answer but also act: qualify leads, follow up to a booking.
Multichannel
Telegram bots, web widgets, integrations into client processes.
Products
GraphRAG
A company AI assistant: answers from your documents, price list and catalog citing every fact, books clients for services and reminds them of visits. Website widget, Telegram, Max, API and MCP; SaaS or deployment inside your perimeter.
An assistant that books: how we added clients, schedules and Telegram, Max and website channels to GraphRAG
An assistant that only answers leaves people the hardest part: booking, reminding, inviting clients back. We added a Clients module to GraphRAG with services, schedules and message scenarios, connected Telegram, Max and a website widget, and wrote a separate gateway for regular company accounts. Here are the decisions we made, what we threw away and where the limits are.
Read →An agent instead of a script: we moved an AI assistant's logic into data and tested it on 300 questions
Knowledge-base assistants are usually built as a pipeline (router → retrieval → answer), and every new kind of question adds a branch. In GraphRAG we replaced the pipeline with an agent that has eight tools, and moved everything that must always happen into a versioned, tested JSON harness. How it works, what a blind comparison on 300 questions showed, and where the agent still loses.
Read →Have a project in this area?
Tell us what you need — we will suggest a format: subscription, turnkey deployment or a lab pilot.